Rag - DEV Community

DEV Community

#rag

Retrieval augmented generation, or RAG, is an architectural approach that can improve the efficacy of large language model (LLM) applications by leveraging custom data.

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
I made my AI agent's notes vault retrievable: 35 MB embedder, llama.cpp reranker, corrections as regression tests

I made my AI agent's notes vault retrievable: 35 MB embedder, llama.cpp reranker, corrections as regression tests

Comments 1
2 min read
Evaluating Staged Retrieval for E-commerce Search with Go and Freshness Gates

Evaluating Staged Retrieval for E-commerce Search with Go and Freshness Gates

Comments
7 min read
Course Tutor Retrieval: Staging Context for Predictable Response Latency

Course Tutor Retrieval: Staging Context for Predictable Response Latency

Comments
7 min read
Citation-Traced Retrieval Architecture Explained (for Real-Estate Listing Discovery)

Citation-Traced Retrieval Architecture Explained (for Real-Estate Listing Discovery)

Comments
7 min read
Retrieval Architecture for Legal Contract Review: Designing Fallbacks That Stay Traceable

Retrieval Architecture for Legal Contract Review: Designing Fallbacks That Stay Traceable

Comments
6 min read
Retrieval Architecture for Support Knowledge Bases: 4 Observability Signals for Triage

Retrieval Architecture for Support Knowledge Bases: 4 Observability Signals for Triage

Comments
5 min read
Semantic Retrieval Relevance Tuning for Candidate Search with Grounded Evidence

Semantic Retrieval Relevance Tuning for Candidate Search with Grounded Evidence

Comments
3 min read
Retrieval Caching Architecture: Python Reliability for a Privacy-Focused Knowledge Manager

Retrieval Caching Architecture: Python Reliability for a Privacy-Focused Knowledge Manager

Comments
4 min read
Semantic Retrieval in Python: A 120ms Budget for Course Support

Semantic Retrieval in Python: A 120ms Budget for Course Support

Comments
7 min read
Why I Chose 3 Retrieval Gates for a Travel Itinerary Planner — Access Rules

Why I Chose 3 Retrieval Gates for a Travel Itinerary Planner — Access Rules

Comments
7 min read
Go Retrieval Architecture: Chunk Boundaries for a Privacy-Focused Personal Knowledge Manager

Go Retrieval Architecture: Chunk Boundaries for a Privacy-Focused Personal Knowledge Manager

Comments
6 min read
Whose permissions does your MCP search run with?

Whose permissions does your MCP search run with?

1
Comments 1
7 min read
Multi-Tenant Help Center Search: 4-Stage Incremental Retrieval With Freshness Checks

Multi-Tenant Help Center Search: 4-Stage Incremental Retrieval With Freshness Checks

Comments
5 min read
How to Keep a Travel Itinerary Planner Fresh — 3 Semantic Retrieval Delete Rules

How to Keep a Travel Itinerary Planner Fresh — 3 Semantic Retrieval Delete Rules

Comments
5 min read
Claims Intake Knowledge Bases: 5 Freshness Rules for Versioned Retrieval

Claims Intake Knowledge Bases: 5 Freshness Rules for Versioned Retrieval

Comments 1
5 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.